ajax-get请求爬虫

# http://vip.stock.finance.sina.com.cn/quotes_service/api/json_v2.php/Market_Center.getHQNodeDataSimple?
# page=1&num=40&sort=symbol&asc=1&node=hs_z&_s_r_a=init

# http://vip.stock.finance.sina.com.cn/quotes_service/api/json_v2.php/Market_Center.getHQNodeDataSimple?
# page=2&num=40&sort=symbol&asc=1&node=hs_z&_s_r_a=page

# http://vip.stock.finance.sina.com.cn/quotes_service/api/json_v2.php/Market_Center.getHQNodeDataSimple?
# page=3&num=40&sort=symbol&asc=1&node=hs_z&_s_r_a=page
# 1  0
# 2  20
# 3  40

# 在控制台上输入起始页码 输入结束页码 然后直接下载对应的页面
# 1   5 enter

import urllib.request
import urllib.parse
# 控制台输入
start_page = int(input('请输入起始页码'))
end_page = int(input('请输入结束页码'))

for i in range(start_page,end_page+1):
    url = 'http://vip.stock.finance.sina.com.cn/quotes_service/api/json_v2.php/Market_Center.getHQNodeDataSimple?'
    data = {
        # 1 2  3  4  5
        # 0 20 40 60 80
        'page':i,
        'num':40,
        'sort':'symbol',
        'asc' :1 ,
        'node':'hs_z',
        '_s_r_a':'auto'
    }
    data = urllib.parse.urlencode(data)
    url = url + data

    headers = {
        # 'Accept': '*/*',
        # 'Accept-Encoding': 'gzip, deflate',
        # 'Accept-Language': 'zh-CN,zh;q=0.9',
        # 'Connection': 'keep-alive',
        # 'Content-type': 'application/x-www-form-urlencoded',
        'Cookie': 'SINAGLOBAL=211.95.6.66_1577409045.527673; UOR=www.baidu.com,mil.news.sina.com.cn,; UM_distinctid=16f7ffc229fd9-07ab930e788b21-55123811-13c680-16f7ffc22a01b1; SCF=AqlPPQaSiKAjYtDJwiOk-ql3lmkIXrAmKCxwK59S3hGvGJaHqyXiQuQYZGttaTyG45fTRP1WiRoDOXQQH1AVnOA.; U_TRS1=00000042.b9506d71.5e1fb5c6.8d3a2545; SGUID=1579153764544_46559084; MONEY-FINANCE-SINA-COM-CN-WEB5=; Apache=211.95.6.66_1590389862.243783; SUB=_2A25zzxw2DeRhGeRO4lUZ9CfKyD2IHXVQvQr-rDV_PUNbm9AKLW_YkW9NUEWLNhO4eQaVWlXcufY1FiB3oF1hHZl2; SUBP=0033WrSXqPxfM725Ws9jqgMF55529P9D9W5a3d.cJpuu0Eyyzuhq1yXs5NHD95QEeh.N1hB4SoepWs4Dqcj4i--fiKnEi-zEi--ciKnfi-2Ei--Xi-zRiKy8i--fiKnpiKysi--Ri-2NiKnpi-eEi-zNi-eEi-zN; ALF=1621925862; ULV=1590389920562:4:2:2:211.95.6.66_1590389862.243783:1590386277916',
        'Host': 'vip.stock.finance.sina.com.cn',
        'Referer': 'http://vip.stock.finance.sina.com.cn/mkt/',
        'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.138 Safari/537.36'

    }

    request = urllib.request.Request(url=url,headers=headers)
    response = urllib.request.urlopen(request)
    # content = response.read()
    content = response.read().decode('utf-8')
    with open('gupiao_' + str(i)+'.json','w',encoding='utf-8')as fp:
        fp.write(str(content))
猜你喜欢
